code-reviewer - AI Code Review Assistant 🔍

Built for AI agent developers who care about code quality.

An intelligent code review assistant that analyzes your codebase and provides detailed, actionable feedback on:

• - 🛡️ Security vulnerabilities
• ⚡ Performance bottlenecks
• 🧹 Code smells and anti-patterns
• ✨ Best practices adherence
• 📚 Documentation quality

🎯 Why code-reviewer?

When building AI agents with OpenClaw, code quality matters more than ever:

• - Agents often run with elevated permissions
• Security vulnerabilities can be exploited by malicious prompts
• Performance issues compound when agents loop
• Maintainability is critical for evolving agent behavior

code-reviewer understands these unique challenges and provides tailored advice.

🚀 Quick Start

Review a single file

Tell your agent:

"Review the code quality of src/agent.js"

Review an entire directory

"Analyze all Python files in ./skills/my-skill/"

Get a detailed report

"Generate a full code review report for the current project"

📋 What Gets Checked

Security 🛡️

• - Injection vulnerabilities - Command injection, path traversal, eval usage
• Sensitive data exposure - Hardcoded secrets, API keys in code
• Unsafe dependencies - Known CVEs in package.json/requirements.txt
• Permission issues - Overly broad file access, unnecessary privileges

Performance ⚡

• - Inefficient algorithms - O(n²) when O(n) exists, unnecessary loops
• Memory leaks - Unreleased resources, closure traps
• Blocking operations - Sync file I/O in async contexts
• Redundant computations - Repeated calculations, unnecessary allocations

Code Quality 🧹

• - Code smells - Long functions, deep nesting, duplicated code
• Naming conventions - Inconsistent or unclear variable names
• Dead code - Unused imports, unreachable statements
• Magic numbers - Hardcoded values without explanation

Best Practices ✨

• - Error handling - Unhandled promises, swallowed exceptions
• Testing - Missing tests, low coverage areas
• Documentation - Missing docstrings, unclear comments
• Type safety - Missing type annotations (TypeScript/Python)

🎨 Output Format

Terminal Summary

CODEBLOCK0

Detailed Markdown Report

Saved to code-review-report.md:

CODEBLOCK1

⚙️ Configuration

Create .codereview.json in your project root for custom rules:

CODEBLOCK2

🧠 How It Works

1. 1. Parse - Reads your code files using OpenClaw's read tool
2. Analyze - Uses AI to understand code structure and intent
3. Detect - Applies security, performance, and quality rules
4. Report - Generates actionable findings with fix suggestions
5. Learn - Adapts to your codebase patterns over time

🌟 Features

Multi-Language Support

• - ✅ JavaScript / TypeScript
• ✅ Python
• ✅ Go
• ✅ Rust
• ✅ Shell scripts
• 🔄 More languages coming soon

Smart Context Awareness

Understands your project type:

• - OpenClaw skills and plugins
• Express/Fastify APIs
• React/Vue frontends
• CLI tools
• Lambda functions

Incremental Reviews

Reviews only changed files in Git:

"Review my latest changes"

Team Integration

Share review reports with your team:

• - Export to GitHub PR comments
• Slack/Discord notifications
• Email summaries

💡 Usage Examples

Example 1: Pre-commit Review

CODEBLOCK3

Output:
CODEBLOCK4

Example 2: Security Audit

CODEBLOCK5

Output:
CODEBLOCK6

Example 3: Performance Check

CODEBLOCK7

Output:

⚡ Performance Analysis
━━━━━━━━━━━━━━━━━━━━━

Found 3 optimization opportunities:

1. Line 45: O(n²) loop - use Map for O(n)
2. Line 67: Sync file read blocks event loop
3. Line 89: Regex compiled in hot path

Estimated improvement: 85% faster

🔒 Privacy & Security

• - ✅ Runs locally - Your code never leaves your machine
• ✅ No telemetry - Zero data collection
• ✅ Open source - Audit the code yourself
• ✅ Safe analysis - Never executes your code

📦 Installation

Via ClawHub (Recommended)

CODEBLOCK9

Manual Installation

CODEBLOCK10

🤝 Contributing

Found a bug? Have a feature idea?

• - 🐛 Report issues: GitHub Issues
• 💡 Suggest features: Discussions
• 🔧 Submit PRs: Contributing Guide

📜 License

MIT License - see LICENSE for details.

🙏 Acknowledgments

Built with ❤️ by 翠花 for the OpenClaw community.

Special thanks to:

• - OpenClaw team for the amazing framework
• ClawHub for making skill distribution easy
• Early adopters for feedback and bug reports

📞 Support

• - 📖 Documentation: Full docs
• 💬 Discord: Join #code-reviewer
• 📧 Email: support@your-domain.com